Research Article
ASCF: Optimization of the Apriori Algorithm Using Spark-Based Cuckoo Filter Structure
| Input: D = Transactional Dataset, min_sup = minimum support. | | Output: 1-frequent items = All singleton frequent items’ RDD | | Foreach transaction T in D | | map (line offset, T) | | flatmap (T, get items) | | Foreach item in T | | map (item, 1) | | End Foreach | | End flatMap | | End map | | End Foreach | | ReduceByKey() | | End ReduceByKey | | 1-frequent items = filter (findFrequent (min_sup)) | | Items = 1-frequent items. Keys () | | Cf = Cuckoofilter (items) | | shared_data = broadcast (Cf) |
|